1995/01/01 by T. Kugarajah, Tharmarajah Kugarajah, Qinghua Zhang
Computer Science · #Image and Signal Denoising Methods
paper · doi:10.1109/72.471353
Pati and Krishnaprasad (1990) first studied the connection between neural networks and wavelet transforms. Zhang and Benveniste (1992) gave a different treatment of this connection. However, the problem of constructing multidimensional wavelet frames for use in neural networks has not been satisfactorily studied. In this paper, one-dimensional wavelet frame is generalized to the multidimensional case by using single-scaling and multiscaling parameters. The construction of multidimensional wavelet frames is also discussed. These results provide more insight on the use of wavelets in neural networks.